| { | |
| "best_metric": 0.8678839206695557, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-1_180-samples_config-1_full/checkpoint-102", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 221, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 1.8599413633346558, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 2.4463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 1.833052158355713, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 2.4612, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.6978809833526611, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 2.3721, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 1.4371284246444702, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 2.4276, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.5903985500335693, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 2.3844, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 1.4731156826019287, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 2.3334, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 1.771949291229248, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 2.407, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 1.3503313064575195, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 2.2979, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 1.157110571861267, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 2.203, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.1026484966278076, | |
| "eval_runtime": 14.4876, | |
| "eval_samples_per_second": 2.485, | |
| "eval_steps_per_second": 2.485, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 1.3301715850830078, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 2.0969, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 1.259554386138916, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 2.0305, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 1.5547571182250977, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 2.0104, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.7977235913276672, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.8823, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.8060275912284851, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.8781, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.9416623711585999, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.731, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.8895557522773743, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.6781, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 1.097531795501709, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.5129, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.163671612739563, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4704, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.3811559677124023, | |
| "eval_runtime": 14.494, | |
| "eval_samples_per_second": 2.484, | |
| "eval_steps_per_second": 2.484, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.8870032429695129, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.3692, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.7472333908081055, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.2896, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.6845778822898865, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.1216, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.5498849153518677, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.1412, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.5651798248291016, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 1.0464, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.4332716166973114, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 1.122, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.4936637878417969, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 1.0392, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.43528568744659424, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.9871, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0200375318527222, | |
| "eval_runtime": 14.4985, | |
| "eval_samples_per_second": 2.483, | |
| "eval_steps_per_second": 2.483, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.4513109028339386, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 0.9526, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.41243019700050354, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 1.0417, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.4456249177455902, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 1.0005, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.40490710735321045, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 1.0048, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.44319161772727966, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.9497, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.515173614025116, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 0.9455, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.4636778235435486, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.9262, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.42171335220336914, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.9468, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.49789193272590637, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8739, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.9493206739425659, | |
| "eval_runtime": 14.4907, | |
| "eval_samples_per_second": 2.484, | |
| "eval_steps_per_second": 2.484, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.4892933964729309, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.8948, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.5443432331085205, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.8842, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.5840004086494446, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.9197, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.6501716375350952, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.8402, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.634289562702179, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.8902, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.6945217251777649, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.8274, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.8182103633880615, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.8483, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.686166524887085, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.8392, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.8938006162643433, | |
| "eval_runtime": 14.487, | |
| "eval_samples_per_second": 2.485, | |
| "eval_steps_per_second": 2.485, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.5784333348274231, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.7844, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.5154232382774353, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.7958, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.5261495113372803, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.77, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.7000530958175659, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.778, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.661331057548523, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.7242, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.6559342741966248, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.6843, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.6252526044845581, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.7715, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.6797327399253845, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.7677, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.6956156492233276, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7701, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.8678839206695557, | |
| "eval_runtime": 14.4908, | |
| "eval_samples_per_second": 2.484, | |
| "eval_steps_per_second": 2.484, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.6819887757301331, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.607, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.728116512298584, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.6738, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.7400087714195251, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.6533, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.7825706005096436, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.6729, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.7726975083351135, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.6504, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.9203025102615356, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.6824, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.8728311657905579, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.5946, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.7805665135383606, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.6585, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.8811736702919006, | |
| "eval_runtime": 14.5048, | |
| "eval_samples_per_second": 2.482, | |
| "eval_steps_per_second": 2.482, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.7518650889396667, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.6328, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.756417453289032, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.5447, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 1.00335693359375, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.5357, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 1.0047552585601807, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.5168, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 1.0003563165664673, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.5044, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.9068002700805664, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.4975, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 1.0071266889572144, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.4952, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 1.0220940113067627, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.5385, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.9211863875389099, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.5569, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.944381594657898, | |
| "eval_runtime": 14.4988, | |
| "eval_samples_per_second": 2.483, | |
| "eval_steps_per_second": 2.483, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.9372286200523376, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.4125, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.9282939434051514, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.3796, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 1.7600594758987427, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.3814, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 1.366844892501831, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.4457, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 1.1296334266662598, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.3892, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.9932205080986023, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.335, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.9950076341629028, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.4107, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 1.361164927482605, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.3568, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.1292650699615479, | |
| "eval_runtime": 14.4896, | |
| "eval_samples_per_second": 2.485, | |
| "eval_steps_per_second": 2.485, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 1.1792492866516113, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.3044, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 1.284213900566101, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.2711, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 1.5250815153121948, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.229, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 1.5420873165130615, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.2657, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 1.202687382698059, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.2613, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 1.0986077785491943, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.2551, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 1.2473537921905518, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.2707, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 1.1692489385604858, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.2574, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.0944453477859497, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.2586, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.2245930433273315, | |
| "eval_runtime": 14.4978, | |
| "eval_samples_per_second": 2.483, | |
| "eval_steps_per_second": 2.483, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 1.0640273094177246, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.1858, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.2826106548309326, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.1529, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 2.205976963043213, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.1703, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 1.7023367881774902, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.1662, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 1.1546049118041992, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.1723, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 1.2123464345932007, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.214, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 1.1112364530563354, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.1793, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 1.2231030464172363, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.1738, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.3852301836013794, | |
| "eval_runtime": 14.5067, | |
| "eval_samples_per_second": 2.482, | |
| "eval_steps_per_second": 2.482, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.8699629306793213, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.1428, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.9064222574234009, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.1099, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 1.208193302154541, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.1161, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 1.4693230390548706, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.1262, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 1.401238203048706, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.1222, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 1.4697661399841309, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.1146, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 1.160336971282959, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.1332, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 1.0867139101028442, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.1213, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.0930207967758179, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.1252, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.4785667657852173, | |
| "eval_runtime": 14.5061, | |
| "eval_samples_per_second": 2.482, | |
| "eval_steps_per_second": 2.482, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.8999132513999939, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.0837, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 1.1762475967407227, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.0927, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 1.3715417385101318, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.0992, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 1.5628798007965088, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.1002, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.522217869758606, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.0923, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 1.2492084503173828, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.1044, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 0.8633227944374084, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.0894, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 1.0648692846298218, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.1, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.6061919927597046, | |
| "eval_runtime": 14.4907, | |
| "eval_samples_per_second": 2.484, | |
| "eval_steps_per_second": 2.484, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 2.814245084122317e+16, | |
| "train_loss": 0.7742039412260056, | |
| "train_runtime": 2086.1118, | |
| "train_samples_per_second": 3.26, | |
| "train_steps_per_second": 0.407 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 850, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 7, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.814245084122317e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |